Saved in:
Bibliographic Details
Main Authors: Li, Jiayun, Hua, Wen, Fan, Shiqi, Jin, Fengmei, Jiang, Haiyang, Li, Xue
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.18255
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917507992911872
author Li, Jiayun
Hua, Wen
Fan, Shiqi
Jin, Fengmei
Jiang, Haiyang
Li, Xue
author_facet Li, Jiayun
Hua, Wen
Fan, Shiqi
Jin, Fengmei
Jiang, Haiyang
Li, Xue
contents Temporal Entity Alignment (TEA), which aims to identify equivalent entities across Temporal Knowledge Graphs (TKGs), is crucial for integrating knowledge facts from multiple sources. However, existing TEA models often fail to capture the orthogonal yet complementary effects between structural and temporal features, and typically overlook the importance of information richness, a key factor for effective message passing in neural feature encoders. To address these limitations, we propose the RCTEA framework, which jointly models both structural and temporal aspects of TKGs for entity alignment. Specifically, we design a richness-guided attention mechanism along with an adaptive weighting strategy to facilitate effective feature fusion. To ensure robust alignment despite noisy entity contexts, we introduce a dual-view neighborhood consensus algorithm that jointly refines the feature encoders to enforce local structural consistency of the predicted alignments. Extensive experiments demonstrate the superiority of RCTEA, achieving state-of-the-art performance on public TEA benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2605_18255
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RCTEA: Richness-guided Co-training for Temporal Entity Alignment
Li, Jiayun
Hua, Wen
Fan, Shiqi
Jin, Fengmei
Jiang, Haiyang
Li, Xue
Information Retrieval
Temporal Entity Alignment (TEA), which aims to identify equivalent entities across Temporal Knowledge Graphs (TKGs), is crucial for integrating knowledge facts from multiple sources. However, existing TEA models often fail to capture the orthogonal yet complementary effects between structural and temporal features, and typically overlook the importance of information richness, a key factor for effective message passing in neural feature encoders. To address these limitations, we propose the RCTEA framework, which jointly models both structural and temporal aspects of TKGs for entity alignment. Specifically, we design a richness-guided attention mechanism along with an adaptive weighting strategy to facilitate effective feature fusion. To ensure robust alignment despite noisy entity contexts, we introduce a dual-view neighborhood consensus algorithm that jointly refines the feature encoders to enforce local structural consistency of the predicted alignments. Extensive experiments demonstrate the superiority of RCTEA, achieving state-of-the-art performance on public TEA benchmarks.
title RCTEA: Richness-guided Co-training for Temporal Entity Alignment
topic Information Retrieval
url https://arxiv.org/abs/2605.18255